{"total":61,"rows":[{"id":"2503.07265","title":"WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation","created":"2025-03-10","cited_by_count":204,"area":null},{"id":"2410.23123","title":"On Memorization of Large Language Models in Logical Reasoning","created":"2024-10-30","cited_by_count":117,"area":"lr"},{"id":"2505.02567","title":"Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities","created":"2025-05-05","cited_by_count":85,"area":null},{"id":"2506.02161","title":"TIIF-Bench: How Does Your T2I Model Follow Your Instructions?","created":"2025-06-02","cited_by_count":69,"area":null},{"id":"2508.17472","title":"T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation","created":"2025-08-24","cited_by_count":38,"area":"lr"},{"id":"2509.03516","title":"Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?","created":"2025-09-03","cited_by_count":34,"area":null},{"id":"2410.18013","title":"Scalable Ranked Preference Optimization for Text-to-Image Generation","created":"2024-10-23","cited_by_count":33,"area":"alignment"},{"id":"2505.23493","title":"R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation","created":"2025-05-29","cited_by_count":32,"area":null},{"id":"2508.17298","title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","created":"2025-08-24","cited_by_count":28,"area":"lr"},{"id":"2605.28091","title":"Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation","created":"2026-05-27","cited_by_count":22,"area":null},{"id":"2501.07493","title":"Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards","created":"2025-01-13","cited_by_count":20,"area":null},{"id":"2412.06745","title":"ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities","created":"2024-12-09","cited_by_count":15,"area":null},{"id":"2412.04300","title":"T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts","created":"2024-12-05","cited_by_count":14,"area":null},{"id":"2505.15249","title":"Fooling the LVLM Judges: Visual Biases in LVLM-Based Evaluation","created":"2025-05-21","cited_by_count":10,"area":"mllm"},{"id":"2603.28718","title":"Stepwise Credit Assignment for GRPO on Flow-Matching Models","created":"2026-03-30","cited_by_count":10,"area":"diffusion"},{"id":"2411.17066","title":"Relations, Negations, and Numbers: Looking for Logic in Generative Text-to-Image Models","created":"2024-11-26","cited_by_count":9,"area":null},{"id":"2507.07207","title":"Scaling can lead to compositional generalization","created":"2025-07-09","cited_by_count":7,"area":null},{"id":"2508.05776","title":"Whither symbols in the era of advanced neural networks?","created":"2025-08-07","cited_by_count":7,"area":null},{"id":"2512.02161","title":"FineGRAIN: Evaluating Failure Modes of Text-to-Image Models with Vision Language Model Judges","created":"2025-12-01","cited_by_count":7,"area":"mllm"},{"id":"2505.05678","title":"InstanceGen: Image Generation with Instance-level Instructions","created":"2025-05-08","cited_by_count":6,"area":null},{"id":"2505.16915","title":"DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2510.10023","title":"Skill-Targeted Adaptive Training","created":"2025-10-11","cited_by_count":6,"area":null},{"id":"2603.08652","title":"CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation","created":"2026-03-09","cited_by_count":6,"area":"lr"},{"id":"2412.10604","title":"EvalGIM: A Library for Evaluating Generative Image Models","created":"2024-12-13","cited_by_count":5,"area":null},{"id":"2506.09082","title":"AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models","created":"2025-06-10","cited_by_count":5,"area":null},{"id":"2601.15286","title":"Iterative Refinement Improves Compositional Image Generation","created":"2026-01-21","cited_by_count":5,"area":"mllm"},{"id":"2412.06089","title":"GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis","created":"2024-12-08","cited_by_count":4,"area":"diffusion"},{"id":"2504.02828","title":"Concept Lancet: Image Editing with Compositional Representation Transplant","created":"2025-04-03","cited_by_count":4,"area":"diffusion"},{"id":"2506.05108","title":"DIMCIM: A Quantitative Evaluation Framework for Default-mode Diversity and Generalization in Text-to-Image Generative Models","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2412.08221","title":"Generate Any Scene: Scene Graph Driven Data Synthesis for Visual Generation Training","created":"2024-12-11","cited_by_count":3,"area":"diffusion"},{"id":"2505.00759","title":"Multimodal Language Models as Text-to-Image Model Evaluators","created":"2025-05-01","cited_by_count":3,"area":"mllm"},{"id":"2507.03275","title":"ConceptMix++: Leveling the Playing Field in Text-to-Image Benchmarking via Iterative Prompt Optimization","created":"2025-07-04","cited_by_count":3,"area":null},{"id":"2602.00249","title":"SANEval: Open-Vocabulary Compositional Benchmarks with Failure-mode Diagnosis","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2505.18775","title":"OmniGenBench: A Benchmark for Omnipotent Multimodal Generation across 50+ Tasks","created":"2025-05-24","cited_by_count":2,"area":"mllm"},{"id":"2506.08480","title":"Re-Thinking the Automatic Evaluation of Image-Text Alignment in Text-to-Image Models","created":"2025-06-10","cited_by_count":2,"area":null},{"id":"2508.12919","title":"7Bench: a Comprehensive Benchmark for Layout-guided Text-to-image Models","created":"2025-08-18","cited_by_count":2,"area":null},{"id":"2510.18083","title":"Chimera: Compositional Image Generation using Part-based Concepting","created":"2025-10-20","cited_by_count":2,"area":null},{"id":"2512.00713","title":"Concept-Guided Backdoor Attack on Vision Language Models","created":"2025-11-30","cited_by_count":2,"area":"mllm"},{"id":"2512.17196","title":"UmniBench: Unified Understand and Generation Model Oriented Omni-dimensional Benchmark","created":"2025-12-19","cited_by_count":2,"area":null},{"id":"2503.14358","title":"RFMI: Estimating Mutual Information on Rectified Flow for Text-to-Image Alignment","created":"2025-03-18","cited_by_count":1,"area":"diffusion"},{"id":"2505.18730","title":"Align Beyond Prompts: Evaluating World Knowledge Alignment in Text-to-Image Generation","created":"2025-05-24","cited_by_count":1,"area":null},{"id":"2512.08645","title":"Chain-of-Image Generation: Toward Monitorable and Controllable Image Generation","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2603.03714","title":"Order Is Not Layout: Order-to-Space Bias in Image Generation","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2603.18528","title":"Correlation-Weighted Multi-Reward Optimization for Compositional Generation","created":"2026-03-19","cited_by_count":1,"area":"alignment"},{"id":"2605.14769","title":"Composable Crystals: Controllable Materials Discovery via Concept Learning","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2608.06751","title":"Beyond Starry Night: Shortcut-Aware Control-State Planning for Artist-Grounded Text to Image Generation","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2609.02255","title":"T2LSC-Bench: Benchmarking Localized Semantic Control in Text-to-Image Generation","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2609.35641","title":"Verifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts","created":"2026-09-28","cited_by_count":1,"area":"mllm"},{"id":"2509.17907","title":"MEF: A Systematic Evaluation Framework for Text-to-Image Models","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2510.23020","title":"M$^{3}$T2IBench: A Large-Scale Multi-Category, Multi-Instance, Multi-Relation Text-to-Image Benchmark","created":"2025-10-27","cited_by_count":0,"area":null},{"id":"2602.16689","title":"Are Object-Centric Representations Better At Compositional Generalization?","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.10210","title":"Delta-K: Boosting Multi-Instance Generation via Cross-Attention Augmentation","created":"2026-03-10","cited_by_count":0,"area":"diffusion"},{"id":"2603.19676","title":"ATHENA: Adaptive Test-Time Steering for Improving Count Fidelity in Diffusion Models","created":"2026-03-20","cited_by_count":0,"area":"diffusion"},{"id":"2604.25358","title":"Benchmarking Layout-Guided Diffusion Models through Unified Semantic-Spatial Evaluation in Closed and Open Settings","created":"2026-04-28","cited_by_count":0,"area":"diffusion"},{"id":"2606.05949","title":"Faithful, Enriched, and Precise: Benchmarking Natural-Science Illustration Generation by T2I models","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.19941","title":"Compositionality Emerges in a Narrow Depth-Connectivity Regime: Architecture Constraints and Solution Manifolds","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.03831","title":"How Do Diffusion Classifiers Decide? A Bias-Centric Evaluation","created":"2026-07-04","cited_by_count":0,"area":"mllm"},{"id":"2607.26411","title":"Do Unified Multimodal Models Think in One Space? A Lens Through Cross-Branch Steering","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.12426","title":"Large Language Models Can Follow Instructions, But Not Many at Once: Phase Transitions in Compositional Constraint Satisfaction","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.24112","title":"Scalable Question-Centric Text-to-Image Evaluation: Reliable Ranking, Fine-Grained Diagnosis, and Cost-Aware Routing","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2610.16224","title":"Look Back to Move Forward: Learning to Revisit for Agentic Compositional Image Generation","created":"2026-10-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}